Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{169524,
        author = {Kritika Tripathi and Devanshi Malik and Sheenam Naaz},
        title = {RAG-Driven Drug Recommendations: A Novel Approach to Personalized Medicine},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {1964-1971},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169524},
        abstract = {Drug recommendation systems have the potential to significantly improve personalized medicine by tailoring therapeutic options to individual patient profiles and medical histories. However, these systems often face challenges in accurately synthesizing large, diverse sources of biomedical information. To improve personalized medicine, this paper introduces a drug recommendation framework powered by using Retrieval-Augmented Generation (RAG) technique. By combining a retrieval mechanism and a generative model, the system effectively combines patient data with a rich biological literature to provide specific medication recommendations. Based on experimental results, the RAG-based approach not only increases the performance of recommendations but also enhances interpretability by informing doctors about relevant treatment choices and why each recommendation came from. This method appears the feasible way for doing precision medicine and informed clinical performance in numerous healthcare situation.},
        keywords = {drug recommendation, machine learning, NLP, Retrieval-Augmented Generation},
        month = {November},
        }